CUMIN recently hosted its first paper reading of Michaelmas term 2019 in the Department of Engineering, on the paper entitled “Counterfactual Fairness” by Kusner, Matt J., et al. The paper was presented by 4th year Information Engineer and CUMIN Chairman Bruno Mlodozeniec. The full paper can be found here, and the abstract is presented below.
Come for our next weekly paper reading session, this Wednesday (30 Oct) 2pm at the Department of Engineering, North Room, on the recently published OpenAI paper “Solving Rubik’s cube with a robot hand” (website) (paper), presented by CUMIN President Henry Pulver. See you there!
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.